Inference provider
Catalogue
Available models
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| nebius/fp8 | 203K | $1.40 | $4.40 | — | — | 100.00% | |
| nebius/fp4 | 1.0M | $1.40 | $4.40 | — | — | 95.50% | |
| nebius/fp8 | 110K | $0.10 | $0.30 | — | — | 96.07% | |
| nebius/fp8 | 131K | $1.00 | $3.00 | — | — | 100.00% | |
| nebius/fp4 | 262K | $0.95 | $4.00 | — | — | 100.00% | |
| nebius/fp8 | 262K | $0.06 | $0.24 | — | — | 97.09% | |
| nebius/fp8 | 262K | $0.20 | $0.60 | — | — | 86.16% | |
| nebius/fp8 | 262K | $0.10 | $0.30 | — | — | 90.07% | |
| nebius | 32K | $0.01 | $0.00 | — | — | 100.00% | |
| nebius/fp4 | 131K | $0.15 | $0.60 | — | — | 100.00% |